INDEX

Explanations

references to historical events and significant figures

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 recently

-0.15

/cms

-0.15

(strip

-0.15

atten

-0.15

æķ

-0.14

EDITOR

-0.14

onta

-0.14

 Eastern

-0.14

acular

-0.14

Eastern

-0.14

POSITIVE LOGITS

-era

0.18

era

0.17

0.16

agate

0.15

 decades

0.15

 distr

0.14

UNET

0.14

Ð¾ÑĢÐ¾ÑĤ

0.14

VICE

0.14

å¹´ä»£

0.14

Activations Density 0.458%

references to historical events and significant figures

No Comments

No Known Activations